ML-optimized VPP controller for battery powered EV charging networks

The VPP controller uses ML to optimize power distribution among grid, battery storage, and EV charging stations, addressing inefficiencies in variable power sources and reducing maintenance costs by predicting power output and demand.

US12646943B2Active Publication Date: 2026-06-02BANPU INNOVATION & VENTURES LLC
View PDF 12 Cites 0 Cited by

Patent Information

Authority / Receiving Office
US · United States
Patent Type
Patents(United States)
Current Assignee / Owner
BANPU INNOVATION & VENTURES LLC
Filing Date
2023-08-31
Publication Date
2026-06-02

AI Technical Summary

Technical Problem

Existing power systems struggle to efficiently manage variable power sources like solar and wind power plants and ensure reliable power supply to consumers due to unpredictable power generation, leading to inefficiencies and increased maintenance costs.

Method used

A VPP controller utilizing machine learning algorithms to predict power output and demand, optimizing power distribution among a power grid, battery storage systems, EV charging stations, and independent power plants, by training a ML model with time-series data to generate commands for power import/export and manage energy flow.

Benefits of technology

Enhances power system efficiency, reduces maintenance costs, and extends the lifespan of battery storage systems by optimizing power distribution and utilization of flexible power sources.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure US12646943-D00000_ABST
    Figure US12646943-D00000_ABST
Patent Text Reader

Abstract

A method of operating a virtual power plant (VPP) controller, that manages an electric vehicle (EV) charging station connected to a power grid, a battery storage system, and an independent power plant, includes: obtaining a first data set including time-series information of power output from the independent power plant; training a machine learning (ML) model that predicts power output from the independent power plant over a predetermined prediction horizon; obtaining a second data set including time-series information of: power demand information from the EV charging station; and power availability information from each of the battery storage system, the power grid, and the independent power plant; generating a predicted schedule of power output from the independent power plant over the predetermined prediction horizon; generating a command by inputting the second data set and the predicted schedule into an energy management system (EMS) policy.
Need to check novelty before this filing date? Find Prior Art